© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111867
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    );$
    -0.29
    ADED
    -0.28
    ç½
    -0.28
    herits
    -0.27
    ystate
    -0.26
    ael
    -0.26
    ivant
    -0.26
     dÃ¼ÅŁ
    -0.26
    pped
    -0.24
    fäll
    -0.24
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.27
    èģĶç³»æĸ¹å¼ı
    0.25
    ä½°
    0.25
    çĻ½çĻ½
    0.25
    æ°ij
    0.24
     shovel
    0.24
    ä¸Ģ个æĺ¯
    0.24
    ias
    0.24
     prediction
    0.24
    Prediction
    0.24
    Activations Density 0.005%

    No Known Activations